Pith. sign in

Deep compression autoencoder for efficient high-resolution diffusion models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer

cs.CV · 2025-06-08 · conditional · novelty 6.0

LaTtE-Flow partitions transformer layers into timestep-specific groups for flow matching, activating only one group per sampling step to speed up image generation in unified multimodal models.

citing papers explorer

Showing 1 of 1 citing paper.

  • LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer cs.CV · 2025-06-08 · conditional · none · ref 5

    LaTtE-Flow partitions transformer layers into timestep-specific groups for flow matching, activating only one group per sampling step to speed up image generation in unified multimodal models.